go-extractor/document.go

package extractor

import (
	"fmt"
	"io"
	"log/slog"
	"time"

	"github.com/playwright-community/playwright-go"
)

type Document interface {
	io.Closer
	Node

	URL() string
	Refresh() error
	Content() (string, error)

	WaitForNetworkIdle(timeout *time.Duration) error
}

type document struct {
	node
	pw       *playwright.Playwright
	browser  playwright.Browser
	page     playwright.Page
	detached bool
}

func newDocument(pw *playwright.Playwright, browser playwright.Browser, page playwright.Page) (Document, error) {
	locator := page.Locator("html")

	res := &document{
		node: node{
			locator: locator,
		},
		pw:      pw,
		browser: browser,
		page:    page,
	}

	slog.Info("new document", "url", page.URL(), "locator", locator)

	return res, nil
}
func (d *document) Close() error {
	if d.detached {
		return nil
	}
	return d.page.Close()
}

func (d *document) URL() string {
	return d.page.URL()
}

func (d *document) Content() (string, error) {
	return d.page.Content()
}

func (d *document) Refresh() error {
	resp, err := d.page.Reload()
	if err != nil {
		return fmt.Errorf("failed to reload page: %w", err)
	}

	if resp != nil && resp.Status() != 200 {
		return fmt.Errorf("invalid status code: %d", resp.Status())
	}

	return nil
}

func (d *document) PageEvaluate(expression string) (interface{}, error) {
	return d.page.Evaluate(expression)
}

func (d *document) WaitForNetworkIdle(timeout *time.Duration) error {
	if timeout == nil {
		t := 30 * time.Second
		timeout = &t
	}

	ms := float64(timeout.Milliseconds())
	return d.page.WaitForLoadState(playwright.PageWaitForLoadStateOptions{
		State:   playwright.LoadStateNetworkidle,
		Timeout: &ms,
	})
}